Angelina YangFounder and Host, TwoSetAI · AI builder for visibility and discoverability

Why LLMs belong in the interpretation layer, not execution | Deepak Bapat, CTO @Tabs

23 Jul 2026 · 1 min

Watch on YouTube

1:12

Deepak Bapat argues LLMs work best interpreting data, not running workflows. His finance software skips chat interfaces because users want buttons. The real problem isn't the model, he says, it's feeding it enough context about invoices and merchants so one CFO can manage a $100 million operation.

Chapters

Early on, we made a bet that we didn't want to build a chat interface. Actually, finance people don't really want that. Just go in and click 3 buttons and fix it. If Customer A has an AP portal and Merchant X has signed Customer A and then Merchant Y goes and signs Customer A, we can start to drive insights on how the invoices should look such that they pass the AP portal. Those are the sorts of insights that we can generate. You can't get a standard horizontal AI product. I actually don't think it's just a model problem. I actually do think there is a context problem here. There are some earlier models that actually do a better job job of being able to process contracts with the right context object than newer models with that same context object. There will be a company that grows to $100 million in ARR with one person running finance across all of these various tools. One of our CFO design partners told us, look, the whole reason they've hired me is to blame someone when things go wrong. The other day I was playing around with some new libraries. I actually decided I'm going to go write the code myself, and it was surprising how quickly the skills deteriorated. There was a minute where I was just staring at a blank page being like, "Okay, where do I start?"